🚀 LongCat Dedicated Quantizer

Convert the LongCat-Image family of models to lower precisions (FP8, FP16, BF16).

Memory & Disk Protection: This tool is specifically tuned to survive the massive 11.68 GB single-file transformer shard. It aggressively purges Hugging Face's download cache and PyTorch's RAM buffer after every single step to keep the free Space alive.

Hugging Face Token (Write Access Required)

Your Hugging Face Username

Source Repository

Components to Quantize

Select which folders should be cast to the new precision. Unselected folders will be copied as-is.

text_encoder transformer vae

Target Precision

Target Repository (Auto-generated)

Operation Logs